CVMay 18, 2021

Correlated Adversarial Joint Discrepancy Adaptation Network

arXiv:2105.08808v12 citations
Originality Incremental advance
AI Analysis

This addresses domain shift in knowledge transfer for machine learning applications, representing an incremental improvement.

The paper tackles domain adaptation by proposing CAJNet to minimize joint discrepancy between domains, achieving competitive classification accuracy on benchmark datasets.

Domain adaptation aims to mitigate the domain shift problem when transferring knowledge from one domain into another similar but different domain. However, most existing works rely on extracting marginal features without considering class labels. Moreover, some methods name their model as so-called unsupervised domain adaptation while tuning the parameters using the target domain label. To address these issues, we propose a novel approach called correlated adversarial joint discrepancy adaptation network (CAJNet), which minimizes the joint discrepancy of two domains and achieves competitive performance with tuning parameters using the correlated label. By training the joint features, we can align the marginal and conditional distributions between the two domains. In addition, we introduce a probability-based top-$\mathcal{K}$ correlated label ($\mathcal{K}$-label), which is a powerful indicator of the target domain and effective metric to tune parameters to aid predictions. Extensive experiments on benchmark datasets demonstrate significant improvements in classification accuracy over the state of the art.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes